Structural Process Supervision for Latent Chain-of-Thought Reasoning
Latent reasoning approaches enhance token-level efficiency and robustness by replacing verbose, explicit chain-of-thought (CoT) tokens with compact continuous-space embeddings. However, existing methods lack efficient process supervision over these embeddings, which often leads to representation collapse and uneven inf...
Yi-Qi Li, Xu Chen, Chen Ju et al.
· 0 citations